The Shiny application developed for the week 4 assignment “Shiny Application and Reproducible Pitch” proposes a data vizualization of the Diamonds dataset distribution as well as linear models to model the relationship between carat and price.

The interactive Shiny application gives the ability to the user to set the size of the random sample used to build the models of the carat / price relationship. THe default sample size is set to 100. The Diamonds dataset comprises 53,940 records.

The Shiny application can be found here https://bluebonobo.shinyapps.io/week4shinyapp/

• The calculation done on the server are located in the file server.R locate in github here https://github.com/bluebonobo/coursera_hopkins_developingdataproducts/tree/main/week4/week4ShinyApp
• The application build one linear regression model per cut quality
• Each model is then represented with its error on the scatter plot
• Models can be isolated by selected the type of cut in the legend